Remove borrowed types from FFI; fixed_size_list constructor accepts u32#8658
Merged
Conversation
myrrc
force-pushed
the
myrrc/ffi-no-borrowed
branch
from
1e8875f to
c9c7bde
Compare
myrrc
changed the title
0ax1
reviewed
Jul 6, 2026
0ax1
left a comment
0ax1
left a comment
Contributor
There was a problem hiding this comment.
Most importantly. Run under ASAN/leak sanitizer. And double check whether any benchmarks regress (bc we heap allocate now instead of borrowing in some cases).
Merging this PR will improve performance by 10.44%
|
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | Simulation | compact_sliced[(4096, 90)] |
750 ns | 837.5 ns | -10.45% |
| ❌ | Simulation | chunked_varbinview_opt_canonical_into[(100, 100)] |
305.7 µs | 340.7 µs | -10.25% |
| ⚡ | Simulation | bitwise_not_vortex_buffer_mut[128] |
273.6 ns | 215.3 ns | +27.1% |
| ⚡ | Simulation | chunked_varbinview_into_canonical[(1000, 10)] |
206 µs | 169.8 µs | +21.3% |
| ⚡ | Simulation | bitwise_not_vortex_buffer_mut[1024] |
333.9 ns | 275.6 ns | +21.17% |
| ⚡ | Simulation | bitwise_not_vortex_buffer_mut[2048] |
427.8 ns | 369.4 ns | +15.79% |
| ⚡ | Simulation | rebuild_naive |
105.5 µs | 91.5 µs | +15.27% |
Tip
Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.
Comparing myrrc/ffi-no-borrowed (4e93282) with develop (86c250a)
Footnotes
-
4 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩
Contributor
Author
|
I've reenabled ASAN, and it reports a leak as it should |
myrrc
force-pushed
the
myrrc/ffi-no-borrowed
branch
from
c9c7bde to
33efcfa
Compare
github-actions
Bot
removed
the
action/benchmark
Contributor
Polar Signals Profiling ResultsLatest Run
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 0.938x ➖ How to read Verdict and Engines
datafusion / vortex-file-compressed (0.938x ➖, 0↑ 0↓)
No file size changes detected. |
myrrc
force-pushed
the
myrrc/ffi-no-borrowed
branch
from
33efcfa to
4e93282
Compare
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.956x ➖, 2↑ 0↓)
datafusion / vortex-compact (0.940x ➖, 0↑ 0↓)
datafusion / parquet (0.919x ➖, 2↑ 0↓)
duckdb / vortex-file-compressed (0.933x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.955x ➖, 0↑ 0↓)
duckdb / parquet (0.921x ➖, 2↑ 0↓)
File Size Changes (1 files changed, -0.1% overall, 0↑ 1↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.974x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.980x ➖, 0↑ 0↓)
datafusion / parquet (0.949x ➖, 5↑ 1↓)
datafusion / arrow (0.959x ➖, 1↑ 0↓)
duckdb / vortex-file-compressed (0.963x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.953x ➖, 2↑ 0↓)
duckdb / parquet (0.944x ➖, 3↑ 1↓)
duckdb / duckdb (0.988x ➖, 0↑ 0↓)
File Size Changes (9 files changed, -0.1% overall, 2↑ 7↓)
Totals:
|
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.997x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.008x ➖, 0↑ 0↓)
datafusion / parquet (0.998x ➖, 3↑ 2↓)
duckdb / vortex-file-compressed (1.006x ➖, 2↑ 3↓)
duckdb / vortex-compact (1.003x ➖, 0↑ 2↓)
duckdb / parquet (0.998x ➖, 0↑ 1↓)
duckdb / duckdb (0.985x ➖, 3↑ 1↓)
File Size Changes (6 files changed, -0.1% overall, 4↑ 2↓)
Totals:
|
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.102x ➖, 0↑ 1↓)
datafusion / vortex-compact (0.828x ➖, 2↑ 0↓)
datafusion / parquet (0.993x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.985x ➖, 0↑ 1↓)
duckdb / vortex-compact (0.936x ➖, 0↑ 0↓)
duckdb / parquet (0.954x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) How to read Verdict and Engines
duckdb / vortex-file-compressed (1.005x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.998x ➖, 0↑ 0↓)
duckdb / parquet (1.008x ➖, 0↑ 0↓)
File Size Changes (1 files changed, +0.0% overall, 1↑ 0↓)
Totals:
|
Contributor
Benchmarks: Clickbench Sorted on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.975x ➖, 2↑ 1↓)
datafusion / parquet (0.996x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.043x ➖, 0↑ 1↓)
duckdb / parquet (0.980x ➖, 0↑ 0↓)
duckdb / duckdb (0.992x ➖, 0↑ 0↓)
File Size Changes (201 files changed, -0.0% overall, 106↑ 95↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.943x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.947x ➖, 1↑ 0↓)
datafusion / parquet (0.954x ➖, 0↑ 0↓)
datafusion / arrow (0.917x ➖, 6↑ 0↓)
duckdb / vortex-file-compressed (0.962x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.971x ➖, 0↑ 0↓)
duckdb / parquet (0.980x ➖, 0↑ 0↓)
duckdb / duckdb (0.967x ➖, 1↑ 0↓)
File Size Changes (27 files changed, +0.0% overall, 18↑ 9↓)
Totals:
|
0ax1
reviewed
Jul 6, 2026
Contributor
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.021x ➖, 0↑ 2↓)
datafusion / parquet (1.007x ➖, 0↑ 2↓)
duckdb / vortex-file-compressed (1.023x ➖, 1↑ 5↓)
duckdb / parquet (1.000x ➖, 0↑ 0↓)
duckdb / duckdb (1.002x ➖, 0↑ 0↓)
File Size Changes (104 files changed, -0.0% overall, 38↑ 66↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.068x ➖, 0↑ 3↓)
datafusion / vortex-compact (1.237x ➖, 0↑ 6↓)
datafusion / parquet (1.170x ➖, 1↑ 5↓)
duckdb / vortex-file-compressed (1.100x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.031x ➖, 0↑ 0↓)
duckdb / parquet (1.066x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: Random AccessVortex (geomean): 1.033x ➖ How to read Verdict and Engines
unknown / unknown (1.029x ➖, 0↑ 5↓)
|
Contributor
Benchmarks: Appian on NVMEVerdict: No clear signal (low confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (0.989x ➖, 0↑ 0↓)
datafusion / parquet (0.985x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.979x ➖, 0↑ 0↓)
duckdb / parquet (0.977x ➖, 0↑ 0↓)
duckdb / duckdb (0.978x ➖, 0↑ 0↓)
File Size Changes (4 files changed, -0.0% overall, 1↑ 3↓)
Totals:
|
0ax1
approved these changes
Jul 6, 2026
Contributor
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) How to read Verdict and Engines
datafusion / vortex-file-compressed (1.048x ➖, 0↑ 1↓)
datafusion / vortex-compact (1.062x ➖, 0↑ 1↓)
datafusion / parquet (1.142x ➖, 0↑ 3↓)
duckdb / vortex-file-compressed (1.094x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.107x ➖, 0↑ 0↓)
duckdb / parquet (1.043x ➖, 0↑ 0↓)
|
Contributor
Benchmarks: CompressionVortex (geomean): 1.005x ➖ How to read Verdict and Engines
unknown / unknown (1.021x ➖, 1↑ 7↓)
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
FFI currently has two types of returned objects: ones are owned (inside of which
there's an Arc), others are borrowed (because there's no Arc inside).
One example of the latter is a struct field name which returns a borrowed
vx_string. We initially had a comment
caller shouldn't call the corresponding _free() function on these. This is not
enough as caller can call a _clone() function on a borrowed vx_string which is
UB because we try to increment a strong reference count on a pointer which isn't
an Arc. From a callee's perspective, we can't distinguish owned and borrowed
types, and this creates weird APIs like struct field dtype being owned but name
being borrowed.
This PR removes all borrowed/owned distinction from FFI layer. Each object now
returned from an FFI function is owned. It can be freely cloned, and each must
be freed explicitly with _free() functions.
On another change, fixed size list constructor previously accepted a size_t
(64-bit unsigned integer on most systems) but validated it against u32 because
that's our file format limitation for fixed size lists. This PR changes the
signature so that now it accepts uint32_t as length parameter.
As the changes are significant enough to trigger bugs in our own tests, this PR also re-enables FFI sanitizer tests in CI.